© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9768
    Prev
    Next
    INDEX
    Explanations

    price targets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ی
    0.55
     vaja
    0.49
     डेयरी
    0.49
    Ahora
    0.48
    Más
    0.46
    ]))
    0.46
    ავ
    0.46
     мод
    0.46
    Mapa
    0.45
    étais
    0.45
    POSITIVE LOGITS
     soreness
    0.47
     Bellev
    0.47
    an
    0.47
     per
    0.45
     Schenectady
    0.45
     unge
    0.44
     Gottlieb
    0.43
    𝕙
    0.43
     RetValue
    0.42
    ierst
    0.42
    Activations Density 0.000%

    No Known Activations